Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

SinglePass algorithm based method for achieving tagged corpus-free active prediction of emergency in mobile customer service field

A technology for emergencies and mobile customer service, applied in computing, semantic analysis, natural language data processing, etc.

Active Publication Date: 2018-09-18
CHINA MOBILE ONLINE SERVICES CO LTD
View PDF2 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method not only does not need to manually mark the emergency corpus, but also can solve the problem of proactively predicting emergencies in the field of mobile customer service and improve the quality of service monitoring

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • SinglePass algorithm based method for achieving tagged corpus-free active prediction of emergency in mobile customer service field
  • SinglePass algorithm based method for achieving tagged corpus-free active prediction of emergency in mobile customer service field
  • SinglePass algorithm based method for achieving tagged corpus-free active prediction of emergency in mobile customer service field

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] Attached below Figure 1-9 The method of the present invention is described in detail, and this example implements on the premise of the technical solution of the invention, and provides detailed implementation and specific operation process, but the protection scope of the invention is not limited to the following examples of implementation.

[0036] The purpose of active early warning of emergencies in the field of mobile customer service is to detect emergencies in time, better monitor public opinion, and improve service quality.

[0037] Because there is no marked corpus, the implementation process of the present invention is as follows: first, the mobile customer service emergency corpus is preprocessed, and the unsupervised SinglePass clustering algorithm is used to find out the topic of the emergency, and then the sudden word is searched for, and the sudden event is calculated. Word relevance and the sudden popularity of each topic, and the topic with the highest...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a SinglePass algorithm based method for achieving tagged corpus-free active prediction of an emergency in a mobile customer service field. The method mainly includes six phasesof pre-processing, constructing a sentence vector, clustering based on the SinglePass algorithm, searching emergent words, calculating the emergent word correlation degree and returning an emergency work order. In a phase of pre-processing, work order data in a customer service field are preprocessed through word segmentation, de-stop words, word vector training, and the like. In the phase of constructing the sentence vector, a word vector of each word in a sentence is separately added to obtain the sentence vector by employing a vector addition method. In the phase of clustering based on theSinglePass algorithm, the work order data is clustered to obtain emergency topics by utilizing the SinglePass algorithm and based on the sentence vector. In the phase of searching the emergent words,the emergent words of each topic are obtained based a time series algorithm (Kleinberg). In the phase of calculating the emergent word correlation degree, the correlation degree between the emergent words and the emergent topic heat are obtained by utilizing mutual information. In the phase of returning the emergency work order, a work order containing the emergent words with the highest emergentword correlation degree in a text with a highest emergent topic heat is returned, and the emergency is obtained.

Description

technical field [0001] The invention relates to a method for proactively predicting emergencies in the field of mobile customer service in the field of natural language processing. It specifically relates to a method based on the SinglePass algorithm to realize unlabeled corpus to actively predict emergencies in the field of mobile customer service. Mainly related to patent classification number G06 Calculation; Calculation; Counting G06F Electrical digital data processing G06F17 / 00 Digital computing equipment or data processing equipment or data processing methods especially suitable for specific functions G06F17 / 30 Information retrieval; and its database structure. Background technique [0002] With the explosive growth of data and the rapid development of information technology, how to discover the potential intentions of users through massive data and actively predict emergencies has become the focus of attention. Emergencies refer to events that occur suddenly and attr...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F17/30G06F17/27
CPCG06F40/289G06F40/30
Inventor 徐俊利赵江江薛超范林博赵宁祁泽川魏强谭乃瑜
Owner CHINA MOBILE ONLINE SERVICES CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com